The internet is a web of lies, according to a team of researchers, and its new algorithm aims to find and catch you out if you lie in emails or elsewhere online.
For a team of researchers from Cass Business School in the UK, it seems that the internet is a ‘web of lies’ that requires a new algorithm capable of sniffing out untruths we write online.
In a paper published in the Journal of Management Information Systems, the team has revealed that it has developed such an algorithm, which applied automated text analysis to an archive of business emails.
By analysing their word use, message development and intertextual exchange cues, they were able to detect how much deception was taking place in emails.
Among the team’s findings were that those lying in emails tend to avoid the use of personal pronouns and unnecessary adjectives; over-structure their arguments, and tend to flatter themselves to appear more accommodating and likeable.
According to the researchers, the algorithm is aimed at helping those managers in business better understand emails, while also helping determine whether a business is being scammed.
Dr Tom van Laer of Cass Business School said of its development: “This research opens up the possibility of fraud prevention and deception-detection technology across lots of in-person domains, not just email. Our approach comes from big data – combining statistics with natural language-processing patterns that tip us off to deception. Authorities and companies will now be able to figure out the plausibility of fraud and identify lying individuals.”
Fellow researcher Ko de Ruyter added: “Everybody lies and most companies realise that the customer is not always right. In fact, customers can often be dishonest and it is costing companies a lot of money.
“Our lie detection software can help companies to assess whether their customers bend the truth in their favour and to decide whether they want to continue doing business with them.”
So, if you’re thinking of sending an email to work pretending you’re not feeling well, maybe think again.
Polygraph test image via Shutterstock